[Evals] Add Chinese homonym evals

[yayachenyi]

Thank you for contributing an eval! ♥️

🚨 Please make sure your PR follows these guidelines, failure to follow the guidelines below will result in the PR being closed automatically. Note that even if the criteria are met, that does not guarantee the PR will be merged nor GPT-4 access be granted. 🚨

PLEASE READ THIS:

In order for a PR to be merged, it must fail on GPT-4. We are aware that right now, users do not have access, so you will not be able to tell if the eval fails or not. Please run your eval with GPT-3.5-Turbo, but keep in mind as we run the eval, if GPT-4 gets higher than 90% on the eval, we will likely reject it since GPT-4 is already capable of completing the task.

We plan to roll out a way for users submitting evals to see the eval performance on GPT-4 soon. Stay tuned! Until then, you will not be able to see the eval performance on GPT-4. Starting April 10, the minimum eval count is 15 samples, we hope this makes it easier to create and contribute evals.

Also, please note that we're using Git LFS for storing the JSON files, so please make sure that you move the JSON file to Git LFS before submitting a PR. Details on how to use Git LFS are available here.

Eval details 📑

Eval name

chinese_homonym

Eval description

Check the model's ability to recognize Chinese homonyms, which are words that have the same pronunciation (Hànyǔ Pīnyīn) but different meanings.

What makes this a useful eval?

It's easy for beginners learning Chinese, whether children or foreign language learners, to distinguish whether two different Chinese words have the same pronunciation. However, GPT's performance on this task is noticeably poor. Recognizing Chinese homonyms is a fundamental language skill. It's used to understand the context of content, assist language learners, and recognize typos, given that the mainstream Chinese input method is based on Hànyǔ Pīnyīn (pronunciation), among other reasons. GPT-3.5 scored 0.476 on this task (even worse than a random guess), while GPT-4 achieved 0.7 through the ChatGPT Plus subscription. We can further examine GPT-4's hallucinations by diving deep into the explanations of correct answers, as shown in the following screenshot.

Criteria for a good eval ✅

Below are some of the criteria we look for in a good eval. In general, we are seeking cases where the model does not do a good job despite being capable of generating a good response (note that there are some things large language models cannot do, so those would not make good evals).

Your eval should be:

• Thematically consistent: The eval should be thematically consistent. We'd like to see a number of prompts all demonstrating some particular failure mode. For example, we can create an eval on cases where the model fails to reason about the physical world.
• Contains failures where a human can do the task, but either GPT-4 or GPT-3.5-Turbo could not.
• Includes good signal around what is the right behavior. This means either a correct answer for Basic evals or the Fact Model-graded eval, or an exhaustive rubric for evaluating answers for the Criteria Model-graded eval.
• Include at least 15 high-quality examples.

If there is anything else that makes your eval worth including, please document it below.

Unique eval value

I manually created a diverse set of tests that uncovered GPT's poor performance on Chinese pronunciation. This could lead to further evaluations from different perspectives.

Eval structure 🏗️

Your eval should

• Check that your data is in evals/registry/data/{name}
• Check that your YAML is registered at evals/registry/evals/{name}.yaml
• Ensure you have the right to use the data you submit via this eval

(For now, we will only be approving evals that use one of the existing eval classes. You may still write custom eval classes for your own cases, and we may consider merging them in the future.)

Final checklist 👀

Submission agreement

By contributing to Evals, you are agreeing to make your evaluation logic and data under the same MIT license as this repository. You must have adequate rights to upload any data used in an Eval. OpenAI reserves the right to use this data in future service improvements to our product. Contributions to OpenAI Evals will be subject to our usual Usage Policies (https://platform.openai.com/docs/usage-policies).

• I agree that my submission will be made available under an MIT license and complies with OpenAI's usage policies.

Email address validation

If your submission is accepted, we will be granting GPT-4 access to a limited number of contributors. Access will be given to the email address associated with the merged pull request.

• I acknowledge that GPT-4 access will only be granted, if applicable, to the email address used for my merged pull request.

Limited availability acknowledgment

We know that you might be excited to contribute to OpenAI's mission, help improve our models, and gain access to GPT-4. However, due to the requirements mentioned above and the high volume of submissions, we will not be able to accept all submissions and thus not grant everyone who opens a PR GPT-4 access. We know this is disappointing, but we hope to set the right expectation before you open this PR.

• I understand that opening a PR, even if it meets the requirements above, does not guarantee the PR will be merged nor GPT-4 access be granted.

Submit eval

• I have filled out all required fields of this form
• I have used Git LFS for the Eval JSON data
• (Ignore if not submitting code) I have run pip install pre-commit; pre-commit install and have verified that black, isort, and autoflake are running when I commit and push

Failure to fill out all required fields will result in the PR being closed.

Eval JSON data

Since we are using Git LFS, we are asking eval submitters to add in as many Eval Samples (at least 5) from their contribution here:

View evals in JSON

Eval

{"input":[{"role":"system","content":"下面这句话中是否存在发音一样的中文单词（两个汉字及以上），若存在返回是，若不存在返回否。你只需要输出`是`或者`否`"},{"role":"user","content":"由于她最近在减肥，所以她今晚上决定不吃鱿鱼了。"}],"ideal":["是"]}
{"input":[{"role":"system","content":"下面这句话中是否存在发音一样的中文单词（两个汉字及以上），若存在返回是，若不存在返回否。你只需要输出`是`或者`否`"},{"role":"user","content":"他最近在出差。"}],"ideal":["否"]}
{"input":[{"role":"system","content":"下面这句话中是否存在发音一样的中文单词（两个汉字及以上），若存在返回是，若不存在返回否。你只需要输出`是`或者`否`"},{"role":"user","content":"玲儿去医院看病，医生给开了胃药，但是她不愿意吃，所以都是她妈妈给她喂药。"}],"ideal":["是"]}
{"input":[{"role":"system","content":"下面这句话中是否存在发音一样的中文单词（两个汉字及以上），若存在返回是，若不存在返回否。你只需要输出`是`或者`否`"},{"role":"user","content":"欲穷千里目，更上一层楼。"}],"ideal":["否"]}
{"input":[{"role":"system","content":"下面这句话中是否存在发音一样的中文单词（两个汉字及以上），若存在返回是，若不存在返回否。你只需要输出`是`或者`否`"},{"role":"user","content":"他给她送回家了"}],"ideal":["否"]}
{"input":[{"role":"system","content":"下面这句话中是否存在发音一样的中文单词（两个汉字及以上），若存在返回是，若不存在返回否。你只需要输出`是`或者`否`"},{"role":"user","content":"现在电视里面演的是一场清朝的殿试。"}],"ideal":["是"]}
{"input":[{"role":"system","content":"下面这句话中是否存在发音一样的中文单词（两个汉字及以上），若存在返回是，若不存在返回否。你只需要输出`是`或者`否`"},{"role":"user","content":"这家初创公司发布的新产品原型是一个圆形的扫地机器人。"}],"ideal":["是"]}
{"input":[{"role":"system","content":"下面这句话中是否存在发音一样的中文单词（两个汉字及以上），若存在返回是，若不存在返回否。你只需要输出`是`或者`否`"},{"role":"user","content":"这个网站的会员太贵了，比另外一家的贵。"}],"ideal":["否"]}
{"input":[{"role":"system","content":"下面这句话中是否存在发音一样的中文单词（两个汉字及以上），若存在返回是，若不存在返回否。你只需要输出`是`或者`否`"},{"role":"user","content":"他在农村生活，每天都要自己生火做饭。"}],"ideal":["否"]}
{"input":[{"role":"system","content":"下面这句话中是否存在发音一样的中文单词（两个汉字及以上），若存在返回是，若不存在返回否。你只需要输出`是`或者`否`"},{"role":"user","content":"他在超级猩猩的徐汇区运动群里面，看到了一个昵称叫星星的女孩。"}],"ideal":["是"]}
{"input":[{"role":"system","content":"下面这句话中是否存在发音一样的中文单词（两个汉字及以上），若存在返回是，若不存在返回否。你只需要输出`是`或者`否`"},{"role":"user","content":"华北工业电机厂新的行政楼会在6月20日举行奠基仪式。"}],"ideal":["是"]}
{"input":[{"role":"system","content":"下面这句话中是否存在发音一样的中文单词（两个汉字及以上），若存在返回是，若不存在返回否。你只需要输出`是`或者`否`"},{"role":"user","content":"坏人是一个聋子，把男主锁在了笼子里。"}],"ideal":["是"]}
{"input":[{"role":"system","content":"下面这句话中是否存在发音一样的中文单词（两个汉字及以上），若存在返回是，若不存在返回否。你只需要输出`是`或者`否`"},{"role":"user","content":"知名医生张教授说过，人的一生其实很短暂。"}],"ideal":["是"]}
{"input":[{"role":"system","content":"下面这句话中是否存在发音一样的中文单词（两个汉字及以上），若存在返回是，若不存在返回否。你只需要输出`是`或者`否`"},{"role":"user","content":"老宋忘了晚上有约会，当他赶到的时候女孩已经先走了，他感到很自责。"}],"ideal":["是"]}
{"input":[{"role":"system","content":"下面这句话中是否存在发音一样的中文单词（两个汉字及以上），若存在返回是，若不存在返回否。你只需要输出`是`或者`否`"},{"role":"user","content":"他们在玩的游戏是掼蛋，小明抓完牌了说这把有戏。"}],"ideal":["否"]}
{"input":[{"role":"system","content":"下面这句话中是否存在发音一样的中文单词（两个汉字及以上），若存在返回是，若不存在返回否。你只需要输出`是`或者`否`"},{"role":"user","content":"黄土坡派出所的警察在接到报案后，来找小区的保安调取监控。"}],"ideal":["否"]}
{"input":[{"role":"system","content":"下面这句话中是否存在发音一样的中文单词（两个汉字及以上），若存在返回是，若不存在返回否。你只需要输出`是`或者`否`"},{"role":"user","content":"要是你不答应，晚上我就饿着。"}],"ideal":["否"]}
{"input":[{"role":"system","content":"下面这句话中是否存在发音一样的中文单词（两个汉字及以上），若存在返回是，若不存在返回否。你只需要输出`是`或者`否`"},{"role":"user","content":"生活像一把无情的雕刻刀，改变了我们的样子。"}],"ideal":["否"]}
{"input":[{"role":"system","content":"下面这句话中是否存在发音一样的中文单词（两个汉字及以上），若存在返回是，若不存在返回否。你只需要输出`是`或者`否`"},{"role":"user","content":"我没什么功利心，我要的是大量的空闲时间，能读书、看电视、想想事，我已经有了，应该知足了。"}],"ideal":["否"]}
{"input":[{"role":"system","content":"下面这句话中是否存在发音一样的中文单词（两个汉字及以上），若存在返回是，若不存在返回否。你只需要输出`是`或者`否`"},{"role":"user","content":"他听着雨花隐隐约约地飘落，慢慢地睡着了，雨花穿过窗外轻轻地落下，落到所有的生者和死者身上。"}],"ideal":["否"]}
{"input":[{"role":"system","content":"下面这句话中是否存在发音一样的中文单词（两个汉字及以上），若存在返回是，若不存在返回否。你只需要输出`是`或者`否`"},{"role":"user","content":"厦门大学临海而建，内拥穿过芙蓉隧道，6月是这个城市一年中最美的时候，红红绿绿点缀中更显韵味，一定要去看那“凤凰花开的路口”。"}],"ideal":["否"]}

[usama-openai]

Thanks for submitting this eval! This PR looks good. I'm approving this PR.

[usama-openai]

You should see GPT-4 API access enabled in your account in the next few days.